Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/cloudflarestream.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import base64
   5 import re
   6
   7 from .common import InfoExtractor
   8
   9
  10 class CloudflareStreamIE(InfoExtractor):
  11     _DOMAIN_RE = r'(?:cloudflarestream\.com|(?:videodelivery|bytehighway)\.net)'
  12     _EMBED_RE = r'embed\.%s/embed/[^/]+\.js\?.*?\bvideo=' % _DOMAIN_RE
  13     _ID_RE = r'[\da-f]{32}|[\w-]+\.[\w-]+\.[\w-]+'
  14     _VALID_URL = r'''(?x)
  15                     https?://
  16                         (?:
  17                             (?:watch\.)?%s/|
  18                             %s
  19                         )
  20                         (?P<id>%s)
  21                     ''' % (_DOMAIN_RE, _EMBED_RE, _ID_RE)
  22     _TESTS = [{
  23         'url': 'https://embed.cloudflarestream.com/embed/we4g.fla9.latest.js?video=31c9291ab41fac05471db4e73aa11717',
  24         'info_dict': {
  25             'id': '31c9291ab41fac05471db4e73aa11717',
  26             'ext': 'mp4',
  27             'title': '31c9291ab41fac05471db4e73aa11717',
  28         },
  29         'params': {
  30             'skip_download': True,
  31         },
  32     }, {
  33         'url': 'https://watch.cloudflarestream.com/9df17203414fd1db3e3ed74abbe936c1',
  34         'only_matching': True,
  35     }, {
  36         'url': 'https://cloudflarestream.com/31c9291ab41fac05471db4e73aa11717/manifest/video.mpd',
  37         'only_matching': True,
  38     }, {
  39         'url': 'https://embed.videodelivery.net/embed/r4xu.fla9.latest.js?video=81d80727f3022488598f68d323c1ad5e',
  40         'only_matching': True,
  41     }]
  42
  43     @staticmethod
  44     def _extract_urls(webpage):
  45         return [
  46             mobj.group('url')
  47             for mobj in re.finditer(
  48                 r'<script[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//%s(?:%s).*?)\1' % (CloudflareStreamIE._EMBED_RE, CloudflareStreamIE._ID_RE),
  49                 webpage)]
  50
  51     def _real_extract(self, url):
  52         video_id = self._match_id(url)
  53         domain = 'bytehighway.net' if 'bytehighway.net/' in url else 'videodelivery.net'
  54         base_url = 'https://%s/%s/' % (domain, video_id)
  55         if '.' in video_id:
  56             video_id = self._parse_json(base64.urlsafe_b64decode(
  57                 video_id.split('.')[1]), video_id)['sub']
  58         manifest_base_url = base_url + 'manifest/video.'
  59
  60         formats = self._extract_m3u8_formats(
  61             manifest_base_url + 'm3u8', video_id, 'mp4',
  62             'm3u8_native', m3u8_id='hls', fatal=False)
  63         formats.extend(self._extract_mpd_formats(
  64             manifest_base_url + 'mpd', video_id, mpd_id='dash', fatal=False))
  65         self._sort_formats(formats)
  66
  67         return {
  68             'id': video_id,
  69             'title': video_id,
  70             'thumbnail': base_url + 'thumbnails/thumbnail.jpg',
  71             'formats': formats,
  72         }